RWN: Robust Watermarking Network for Image Cropping Localization

TL;DR

This paper introduces RWN, a robust watermarking network that accurately localizes image cropping and tampering, enhancing digital image integrity verification on social networks.

Contribution

The paper proposes a novel watermarking approach for precise image crop localization and tamper detection, extending prior work that only identified whether an image was cropped.

Findings

RWN achieves high-accuracy crop localization.

The method is robust against common image manipulations.

Tamper detection accuracy is comparable to state-of-the-art methods.

Abstract

Image cropping can be maliciously used to manipulate the layout of an image and alter the underlying meaning. Previous image crop detection schemes only predicts whether an image has been cropped, ignoring which part of the image is cropped. This paper presents a novel robust watermarking network (RWN) for image crop localization. We train an anti-crop processor (ACP) that embeds a watermark into a target image. The visually indistinguishable protected image is then posted on the social network instead of the original image. At the recipient's side, ACP extracts the watermark from the attacked image, and we conduct feature matching on the original and extracted watermark to locate the position of the crop in the original image plane. We further extend our scheme to detect tampering attack on the attacked image. Besides, we explore a simple yet efficient method (JPEG-Mixup) to improve the generalization of JPEG robustness. According to our comprehensive experiments, RWN is the first to provide high-accuracy and robust image crop localization. Besides, the accuracy of tamper detection is comparable with many state-of-the-art passive-based methods.